feat: track logical call statistics across governed calls

src/polygateway/ocr.py

@@ -40,12 +40,14 @@ from polygateway.middleware.retry import StallClock, _failure_reason, backoff_de
 from polygateway.middleware.telemetry import TelemetryEmitter
 from polygateway.ports import OutcomeAwareSelector
 from polygateway.types import (
+    CallStats,
     ChatRequest,
     LLMResponse,
     OcrLayoutResult,
     OcrTextResult,
     TelemetryStatus,
     Usage,
+    _CallContext,
     strip_unsupported_extra_body,
     validate_caller_dimensions,
 )
@@ -176,7 +178,7 @@ class OcrClient:
         dimension_tenant_id, dimensions = validate_caller_dimensions(
             tenant_id, meta, origin="recognize_text(tenant_id=..., meta=...)"
         )
-        outcome = await self._call(
+        outcome, call_stats = await self._call(
             "text", image, session_id, parent_call_id, dimension_tenant_id, dimensions
         )
         result = outcome.result
@@ -187,6 +189,7 @@ class OcrClient:
             latency_ms=outcome.latency_ms,
             call_id=outcome.call_id,
             raw=result.raw,
+            call_stats=call_stats,
         )
 
     async def parse_layout(
@@ -206,7 +209,7 @@ class OcrClient:
         dimension_tenant_id, dimensions = validate_caller_dimensions(
             tenant_id, meta, origin="parse_layout(tenant_id=..., meta=...)"
         )
-        outcome = await self._call(
+        outcome, call_stats = await self._call(
             "layout", image, session_id, parent_call_id, dimension_tenant_id, dimensions
         )
         result = outcome.result
@@ -218,6 +221,7 @@ class OcrClient:
             latency_ms=outcome.latency_ms,
             call_id=outcome.call_id,
             raw=result.raw,
+            call_stats=call_stats,
         )
 
     async def check_health(self) -> dict[str, bool]:
@@ -242,11 +246,14 @@ class OcrClient:
         parent_call_id: str | None,
         tenant_id: str | None,
         meta: dict[str, Any],
-    ) -> _AttemptOutcome:
+    ) -> tuple[_AttemptOutcome, CallStats]:
         if not isinstance(image, bytes):
             raise TypeError("image 必须是 bytes(路径读取/批量拼帧留业务侧,D9)")
         if not image:
             raise ValueError("image 不能为空")
+        # M1 例外: `image` 校验在 `_call` 内而非公开方法,故上下文在该校验
+        # **通过之后**创建——这样设计 §3 的"校验在统计边界外"对 OCR 才成立
+        context = _CallContext(now=self._now)
         if not self._sources:
             raise AllSourcesExhausted(scope=self._scope, reason="no_sources", retry_after_s=0.0)
         fails = 0
@@ -260,10 +267,18 @@ class OcrClient:
                 continue
             async with clock.attempting():
                 outcome = await self._attempt(
-                    kind, image, *picked, reasons, session_id, parent_call_id, tenant_id, meta
+                    kind,
+                    image,
+                    *picked,
+                    reasons,
+                    session_id,
+                    parent_call_id,
+                    tenant_id,
+                    meta,
+                    context,
                 )
             if isinstance(outcome, _AttemptOutcome):
-                return outcome
+                return outcome, context.snapshot()
             fails += 1
             if fails >= self._retry.max_attempts:
                 raise AllSourcesExhausted(
@@ -287,11 +302,14 @@ class OcrClient:
         parent_call_id: str | None,
         tenant_id: str | None,
         meta: dict[str, Any],
+        context: _CallContext,
     ) -> _AttemptOutcome | _FailedAttempt:
         call_id = str(uuid.uuid4())
         started = self._now()
         # 四个 emit 分支(成功/终态拒绝/取消/可重试失败)都必须带调用方维度:
         # 失败行与取消行同样需要租户归属,漏掉任一分支就会写出无归属的行
+        # layout 的 POST + ZIP GET 在同一次 `_invoke` 内,故这里只登记 **1** 次
+        context.register_attempt()
         try:
             result = await self._invoke(kind, image, source, call_id)
             await self._record_quietly(self._breaker.record_success(entry))